Abstract
Currently, global energy consumption is growing. Traditional energy sources are becoming more efficient, but the growth of the world's population leads to a general increase in energy consumption. Thus, according to the forecasts of the International Energy Agency, the forecast for energy consumption for 2030 will be 33.4 trillion kW * h, and by 2050 it will increase to 41.3 trillion kW * h. In this regard, to ensure the growth of global demands, the energy sector needs fundamental changes, namely, decentralization of generation, introduction of smart grids (Smart Grid), and the use of alternative energy sources (solar energy and wind energy). Only in this case will it be possible to radically reduce the cost of electricity. However, the use of alternative energy sources within the framework of the wholesale electricity and capacity market currently operating on the territory of the Russian Federation is impossible without the use of such short-term day-ahead forecast models. This article analyzed the existing methods of short-term forecasting, which are used to build forecasts of the generation of electric energy in solar power plants. And also, their classification was worked out. To date, there is already a fairly large number of prognostic models built within the framework of each of the selected methods for short-term forecasting, and all of them differ in their features. Therefore, to highlight the most promising method for short-term forecasting for further use and development, an analysis of some of the existing prognostic models was carried out. During the study, the accuracy of forecasting for each of the short-term forecasting methods was evaluated and a conclusion was drawn on the prospects for the use and further development of a hybrid statistical-adaptive method.
Keywords
Data mining, forecast, electricity, generation, solar power plants, renewable energy sources.
1. Eroshenko S.A., Khalyasmaa A.I., Snegirev D.A. Approaches to prediction of the flux density of solar energy for SPS. Energoekspert [Energy expert], 2017, no. 5, pp. 28–31. (In Russian)
2. Tolstykh M.A. Frolov A.V. Some current problems in numerical weather prediction. Izvestiya RAN. [Proceedings of the Russian Academy of Sciences], 2005, vol. 41, no. 3, pp. 285–295. (In Russian)
3. Gritsay A.S. Gibridnyy metod kratkosrochnogo prognozirovaniya potrebleniya elektricheskoy energii dlya energosbytovogo predpriyatiya s uchetom meteo faktorov [Hybrid method of short-term forecasting of electric energy consumption for a power sales company taking into account meteorological factors]. Omsk, 2017. 153 p. (In Russian)
4. Zamora R.J., Dutton E.G., Trainer M., McKeen S.A., Wilczak J.M., Hou Y.T. The Accuracy of Solar Irradiance Calculations Used in Mesoscale Numerical Weather Prediction. Monthly Weather Review, 2005, vol. 133, no. 4, pp. 783–792.
5. Gandoman F.H., Aleem S.A., Omar N., Ahmadi A., Alenezi F.Q. Short-term solar power forecasting considering cloud coverage and ambient temperature variation effects. Renewable Energy, 2018, vol. 123, pp. 793–805.
6. Akter N., Islam Md.N. Use of MM5 model for weather forecasting over Bangladesh region. BRAC University Journal, 2007, vol. IV, pp. 75–79.
7. Lazic L., Pejanovic G, Zivkovic M. Wind forecasts for wind power generation using the Eta model. Renewable Energy, 2009, vol. 35, pp. 1236–1243.
8. Kivchun O.R. The vector rank analysis in energy management of military infrastructure objects. Izvestiya Tulskogo gosudarstvennogo universiteta. Tekhnicheskie nauki [Proceedings of Tula State University. Technical sciences]. 2018, no. 11, pp. 550–560. (In Russian)
9. Timchuk S.A., Katyuha I.A. Development of regression coefficient selection quality criterion in power consumption forecasting problems. Vostochno-evropeyskiy zhurnal peredovykh tekhnologiy [Eastern-European Journal of Enterprise Technologies], 2014, vol. 5, no. 8 (71), pp. 16–20. (In Russian)
10. Nadtoka I.I., Demura A.V., Gubskiy S.O., Vakolyuk A.J., Gorbachev V.V. Energy consumption prediction model for temperature and lighting of regional dispatch administrations. Vestnik Samarskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: tekhnicheskie nauki [Bulletin of Samara State Technical University. Technical Sciences Series], 2012, vol. 1 (33), pp. 156–161. (In Russian)
11. Manusov V.Z., Khokhlova S.V. Comparative analysis of two models of electrical load prediction of industrial enterprises based on regression analysis and artificial neural networks. Nauchnyy vestnik Novosibirskogo gosudarstvennogo tekhnicheskogo universiteta [Science bulletin of Novosibirsk State Technical University], 2008, vol. 1 (30), pp. 147–159. (In Russian)
12. Gritsay A.S., Tyunkov D.A. Classification of methods for short-term power consumption forecasting for WECM subjects. Aktualnye voprosy energetiki. Materialy Vserossiyskoy nauchnoy konferentsii studentov, magistrantov, aspirantov [Actual energy issues: Proc. of the All-Russian scientific conference of students, undergraduates, PhD student]. Omsk, OmGTU Publ., 2016, pp. 41–45. (In Russian)
13. Magnus Ya.R., Katyshev P.K., Peresetskiy A.A. Ekonometrika. Nachal'nyy kurs [Econometrics. Initial course]. Moscow, Delo Publ, 2007. 504 p.
14. Bacher P., Madsen H., Nielsen Y.A. Online short-term solar power forecasting. Solar Energy, 2009, vol. 83, no. 10, pp. 1772–1783.
15. Ramakrishna R. Scaglione A. A Compressive Sensing framework for the analysis of Solar Photo-Voltaic Power. Proceedings of 50th Asilomar Conference on Signals, Systems and Computers. PacificGrove, IEEE Publ, 2016, pp. 308–3012.
16. Mora-López L., Martínez-Marchena I., Piliougine M., Sidrach-de-Cardona M. Binding Statistical and Machine Learning Models for Short-Term Forecasting of Global Solar Radiation. Lecture Notes in Computer Science, 2011, vol. 7014, pp. 294–305.
17. Snegirev D.A., Eroshenko S.A., Halyasmaa A.I., Dubaylova V.V. Short-term photovoltaic power plants generation forecasting model. Elektroenergetika glazami molodezhi – 2018: Materialy IX Mezhdunarodnoy molodezhnoy nauchno-tekhnicheskoy konferentsii [Electric power industry through the eyes of youth – 2018: Proc. of the IX International Youth Scientific and Technical Conference]. Kazan, KGEU Publ, 2018, vol. 3, pp. 179–182. (In Russian)
18. Kuznetsov N.P., Lysenko O.V. Statistical analysis of energy indices of solar radiation (Based on the data of Tokmak Solar Power Station). Problemy regionalnoy energetiki [Problems of the regional power industry], 2017, no. 2 (34), pp. 139–147. (In Russian)
19. Kivchun O.R. The method of vector rank analysis of power consumption of regional infrastructure objects. Promyshlennaya energetika [Industrial power engineering], 2018, no. 5, pp. 36–43. (In Russian)
20. Chowdhury B.H., Rahman S. Forecasting sub-hourly solar irradiance for prediction of photovoltaic output Proceedings of IEEE Photovoltaic Specialists Conference. New Orleans, IEEE Publ, 1987, pp. 171–176.
21. Manusov V.Z., Biruikov E.V. Short-term load prediction on the basis of fuzzy neural network and its comparison with other methods. Izvestiya Tomskogo politekhnicheskogo universiteta [Bulletin of Tomsk Polytechnic University], 2006, vol. 309, no. 6, pp. 153–157. (In Russian)
22. Potapov V.I., Gritsay A.S., Tyunkov D.A., Sinitsin G.E. Using neural network for building short) term forecast of electricity load of LLC "Omsk energy retail company". Izvestiya Tomskogo politekhnicheskogo universiteta [Bulletin of Tomsk Polytechnic University], Geo Assets Engineering, 2016, vol. 327, no. 8, pp. 44–51. (In Russian)
23. Haykin S. Neyronnye seti: per. s angl. [Neural networks: translated from English]. Moscow, Williams Publ., 2006, 1104 p. (In Russian)
24. Potapov V.I. On the effectiveness of providing reliability of redundant neural systems with a random period of monitoring and recovery of operability after the neurons failure. Omskiy nauchnyy vestnik [Omsk Scientific Bulletin], 2010, no. 3 (93), pp. 202–203. (In Russian)
25. Vyugin V.V. Matematicheskie osnovy teorii mashinnogo obucheniya i prognozirovaniya [Mathematical foundations of the theory of machine learning and forecasting]. Moscow, MCMNO Publ., 2013, 387 p. (In Russian)
26. Nadtoka I.I., Al-Zihery B.M. Short term load forecasting by using least squares support vector machine theory. Scientific journal Modern problems of science and education, 2013, no. 6. Available at: https://www.science-education.ru/ru/article/ view?id=11213 (accessed 02 March 2019). (In Russian)
27. Eroshenko S., Khalyasmaa A., Snegirev D. Machine learning techniques for short-term solar power stations operational mode planning. E3S Web of Conferences, 2018, vol. 51, doi: 10.1051/e3sconf/20185102004.
28. Singh V.P., Vijay V., Bhatt M.S., Chaturvedi D.K. Generalized neural network methodology for short term solar power forecasting. Proceedings of 13th International Conference on Environment and Electrical Engineering (EEEIC). Wroclaw, IEEE Publ., 2013, doi: 10.1109/eeeic-2.2013.6737883.
29. Chen C., Duan S., Cai T., Liu B. Online 24-h solar power forecasting based on weather type classification using artificial neural network. Solar Energy, 2011, vol. 85, no. 11, pp. 2856–2870.
30. Li L.L., Cheng P., Lin H.C., Dong H. Short-term output power forecasting of photovoltaic systems based on the deep belief net. Advances in Mechanical Engineering, 2017, vol. 9, no. 9, doi: 10.1177/1687814017715983.
31. Stepanov S.M., Iskra N.A. Neural network forecasting of energy generation by solar panels. Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioelektroniki [Proceedings of the Belarusian State University of Informatics and Radioelectronics], 2018, no. 3 (113), pp. 26–31. (In Russian)
32. Vorotyntsev D.V., Tyagunov M.G. Forecasting the Power Output Produced by Photovoltaic Power Plants (for the day ahead) Using Machine Learning Techniques. Vestnik Moskovskogo energeticheskogo instituta [Bulletin of Moscow Power Engineering Institute], 2018, no. 4(4), pp. 53–57. (In Russian)
33. Kryukov O.V., Serebryakov A.V. Forecast of Power Generation Invariant Wind Power Installation by Method of Fuzzy Logic. Aktualnye problemy aviatsii i kosmonavtiki [Topical Issues of Air Transport and Space Technology], 2015, vol. 1, no. 11, pp. 316–318. (In Russian)
34. Gritsay A.S., Tyunkov D.A., Khamitov R.N., Dugin D.D., Sinitsin G.E. Forecast of electricity load via hybrid method on the wholesale power market. Elektroenergetika glazami molodezhi: Materialy VIII Mezhdunarodnoy molodezhnoy nauchno-tekhnicheskoy konferentsii [Electric power industry through the eyes of the youth: Proc. of the VIII International Scientific and Technical Conference]. Samara: SamGTU, 2017, vol. 3, pp. 163–166. (In Russian)
35. Khamitov R.N., Gritsay A.S., Tyunkov D.A., Dugin D.D., Sinitsin G.E. On the method of constructing a learning sample in the problems of short-term forecasting of power consumption with allowance for the criteria of information value and compactness. Promyshlennaya energetika [Industrial power engineering], 2017, no. 8, pp. 23–28. (In Russian)
36. Snegirev D.A., Valiev R.T., Eroshenko S.A., Khalyasmaa A.I. Specific features of photovoltaic power plants generation forecasting. Elektroenergetika glazami molodezhi: Materialy VIII Mezhdunarodnoy molodezhnoy nauchno-tekhnicheskoy konferentsii [Electric power industry through the eyes of the youth: Proc. of the VIII International Scientific and Technical Conference]. Samara: SamGTU, 2017, vol. 3, pp. 139–142. (In Russian)
37. Wu Y.K., Chen C.R., Rahman H.A. A Novel Hybrid Model for Short-Term Fore-casting in PV Power Generation. International Journal of Photoenergy, 2014, vol. 2014, doi: 10.1155/2014/569249.